© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 15857
    Prev
    Next
    INDEX
    Explanations

    activist and list item separators

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens related to medical/health warnings, consequences, resources, or authoritative informational/headline phrases.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    опера
    0.46
    ಾಗಲೇ
    0.45
     Ying
    0.44
     نحل
    0.43
     ಅಭಿಮಾನ
    0.42
     endExpNow
    0.41
    皋
    0.41
     getState
    0.40
    рих
    0.40
     సహాయ
    0.40
    POSITIVE LOGITS
    '
    0.51
    ?
    0.49
    unicorn
    0.47
    虎
    0.46
    Hak
    0.45
    ;
    0.44
    +
    0.44
    .
    0.44
    mates
    0.42
    hak
    0.42
    Activations Density 9.806%

    No Known Activations